Learning Discriminative Correlation Subspace for Heterogeneous Domain Adaptation

Yan, Yuguang; Li, Wen; Ng, Michael K.; Tan, Mingkui; Wu, Hanrui; Min, Huaqing; Wu, Qingyao

doi:10.24963/ijcai.2017/454

Cited by 45 publications

(18 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cross-Domain Landmark Selection (CDLS) [30] identifies the representative landmarks by matching the cross-domain data distributions and reducing the domain discrepancy. Yan et al [36] introduced Discriminative Correlation Analysis (DCA), which jointly optimizes the canonical correlation subspace and the discriminative ability of the classifier. Progressive Alignment (PA) [18] iteratively optimizes the latent feature space by dictionary-sharing sparse coding and reduces the cross-domain distribution discrepancy.…”

Section: Related Workmentioning

confidence: 99%

Prototype-Matching Graph Network for Heterogeneous Domain Adaptation

Wang

Luo

Huang

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Even though the multimedia data is ubiquitous on the web, the scarcity of the annotated data and variety of data modalities hinder their usage by multimedia applications. Heterogeneous domain adaptation (HDA) has therefore arisen to address such limitations by facilitating the knowledge transfer between heterogeneous domains. Existing HDA methods only focus on aligning the crossdomain feature distributions and ignore the importance of maximizing the margin among different classes, which may lead to a suboptimal classification performance. To tackle this problem, in this paper, we propose the Prototype-Matching Graph Network (PMGN), which gradually explores the domain-invariant class prototype representations. Specifically, we build an end-to-end Graph Prototypical Network, which computes the class prototypes through multiple layers of edge learning, node aggregation, and discrepancy minimization. Our framework utilizes the Swap training strategy to provide adequate supervision for training the edge learning component. Moreover, the proposed PMGN can be equipped with the clustering module that utilises the KL-divergence as a distance metric to reduce the distribution difference between the source and target data. Extensive experiments on three HDA tasks (i.e. object recognition, text-to-image classification, and text categorization) demonstrate the superiority of our approach over the state-of-theart HDA methods. CCS CONCEPTS • Computing methodologies → Transfer learning.

show abstract

Section: Related Workmentioning

confidence: 99%

Prototype-Matching Graph Network for Heterogeneous Domain Adaptation

Wang

Luo

Huang

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Additionally, the number of metrics used in different datasets has the discrepancy. For example, AEEEM adopts 69 metrics while NASA [13] has 38. The features included in different datasets are not identical.…”

Section: A Motivationmentioning

confidence: 99%

“…Yan et al [37] proposed a semi-supervised algorithm for heterogeneous domain adaptation by exploiting the theory of optimal transport. The method can also be used to find the optimal discriminative correlation subspace for the source and target data [38].…”

Section: B Heterogeneous Transfer Learning On Software Defect Predictionmentioning

confidence: 99%

Multiview Transfer Learning for Software Defect Prediction

Chen

Yang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Most software defect prediction models usually assume that enough historical training instances with labels are available. Additionally, the training data and the predicted instances should share the same features to ensure the prediction accuracy. However, in practice, there are many datasets with different granularities containing information in different dimensions. Therefore, it is valuable to effectively use the small scale and different dimensions of data as training instances to improve the prediction performance of the model. We propose a heterogeneous data orienting multiview transfer learning for software defect prediction, denoted as MTDP, which can achieve different dimensions and granularities features to automatically learn labels through neural network models. With this multiview transfer method, lots of training instances are provided for software defect prediction model to ensure the effectiveness of training labels. The proposed MTDP method has four main stages: 1) build heterogeneous transfer models; 2) transfer heterogeneous instances to generate quasi-real instances; 3) label quasi-real instances through co-training and then expand the training set; and (4) construct improved software defect prediction models. The experimental results show that the quasi-real instances have similar effects compared with real instances. Moreover, the software defect prediction performance can be improved by introducing the quasi-real instances into the training dataset.INDEX TERMS Multiview transfer learning, software defect prediction, active learning, neural network.

show abstract

“…Most of the feature-representation-transfer learning methods can be used in homogeneous transfer learning [21], [22]. As for the heterogeneous transfer learning, Yan et al [23] proposed to find the discriminative feature subspace inherited from the canonical correlation space between the source and target data. To apply this method into online transfer learning, Yan [24] proposed to mine offline knowledge and online knowledge in different domains by using hedge ensemble.…”

Section: B Feature-representation-transfer Learningmentioning

confidence: 99%

An Adaptive Approach for Ice Detection in Wind Turbine With Inductive Transfer Learning

et al. 2019

View full text Add to dashboard Cite

Ice-accretion on blades of a wind turbine will cause power degradation and threaten the operating safety of the unit. The use of a machine learning method for ice detection is a promising solution. However, it is costly and infeasible to establish a well-trained model for each individual unit. This paper proposes an inductive transfer learning method to address this problem. The inductive transfer learning aims to improve the detection performance by transferring knowledge from a well-established model. As there is a distribution divergence between the source and target domain, most instance-transfer-based learning methods realize the knowledge transfer by re-weighting the instance in the source domain. In this paper, we propose a novel adaptive inductive transfer learning (adaptive ITL) method for wind turbine ice detection. The knowledge transfer is achieved by offering a relatively stable prediction for the target task through the established model trained in source task. Two auxiliary classifiers are then employed to correct the prediction error of the previous prediction. The model in the source domain and two auxiliary classifiers are combined into a whole model to make a further prediction for the target task. The experimental results on ice detection in wind turbine demonstrate that the proposed adaptive ITL method can significantly improve the performance of the basic instance-transfer-based model and is superior to the state-of-the-art inductive transfer learning methods. INDEX TERMS Ice detection, wind turbine, inductive transfer learning, machine learning. I. INTRODUCTION

show abstract

Learning Discriminative Correlation Subspace for Heterogeneous Domain Adaptation

Cited by 45 publications

References 16 publications

Prototype-Matching Graph Network for Heterogeneous Domain Adaptation

Prototype-Matching Graph Network for Heterogeneous Domain Adaptation

Multiview Transfer Learning for Software Defect Prediction

An Adaptive Approach for Ice Detection in Wind Turbine With Inductive Transfer Learning

Contact Info

Product

Resources

About